© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14395
    Prev
    Next
    INDEX
    Explanations

    furniture design and manufacturing

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the word “furniture” (and close variants), effectively detecting mentions of furniture.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    呶
    -2.63
    熥
    -2.63
    en
    -2.39
    eniem
    -2.22
    archiwizowane
    -2.22
    ot
    -2.14
    Ruju
    -2.06
    ଝ
    -2.06
    裥
    -2.05
    瞜
    -2.03
    POSITIVE LOGITS
    .
    2.94
    猹
    2.41
    ubt
    2.19
    ですので
    1.95
     but
    1.92
    decer
    1.89
    obé
    1.88
    menina
    1.88
    醍
    1.85
    逡
    1.84
    Activations Density 0.010%

    No Known Activations